METHOD AND SYSTEM FOR PERSONALIZED MOTION PLANNING IN AUTONOMOUS DRIVING VEHICLES
The present teaching relates to method, system, medium, and implementation of automatic motion planning for an autonomous driving vehicle. Self-aware capability parameters are obtained that are instantiated with respect to a current location of the autonomous driving vehicle and are to be used to estimate the operational capability of the autonomous driving vehicle with respect to the current location. A preference of a passenger present in the autonomous driving vehicle is estimated with respect to vehicle motion. The motion of the autonomous driving vehicle is planned automatically based on the self-aware capability parameters and the preference of the passenger.
1 . A method implemented on a computer having at least one processor, a storage, and a communication platform for motion planning for an autonomous driving vehicle, comprising:
obtaining self-aware capability parameters instantiated with respect to a current location of the autonomous driving vehicle, wherein the self-aware capability parameters are to be used to estimate the operational capability of the autonomous driving vehicle with respect to the current location;
estimating a preference of a passenger present in the autonomous driving vehicle with respect to vehicle motion; and
planning the motion of the autonomous driving vehicle based on the self-aware capability parameters and the preference of the passenger.
2 . The method of claim 1 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying conditions internal to the autonomous driving vehicle that limit the operational capability of the autonomous driving vehicle, the extrinsic capability parameters specifying conditions external to the autonomous driving vehicle that limit the operational capability of the autonomous driving vehicle.
3 . The method of claim 1 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous driving vehicle is currently associated with.
4 . The method of claim 1 , wherein the preference of the passenger with respect to the vehicle motion is estimated based on at least one of:
an explicit indication of the preference;
an reaction of the passenger to the vehicle motion; and
a scenario relevant to the passenger.
5 . The method of claim 4 , wherein the reaction of the passenger is estimated by:
obtaining, via one or more in-situ sensors, sensor data in one or more media types;
obtaining at least one feature associated with the passenger based on the sensor data;
identifying a reaction cue of the passenger based on at least one of
a visual based reaction cue based on some visual feature of the at least one feature, and
an acoustic based reaction cue based on some acoustic feature of the at least one feature; and
obtaining the reaction of the passenger to the vehicle motion based on the reaction cue of the passenger.
6 . The method of claim 5 , wherein the reaction of the passenger to the vehicle motion is further evaluated based on at least one of an express statement, emotional state of the passenger inferred based on the visual and acoustic features of the at least one feature, and a combination thereof.
7 . The method of claim 5 , wherein the scenario relevant to the passenger for inferring the preference of the passenger include at least one of:
a known event scheduled;
an event with an indicated urgency; and
certain information about the passenger.
8 . Machine readable and non-transitory medium having data recorded thereon for route planning for an autonomous driving vehicle, wherein the data, once read by the machine, cause the machine to perform the following:
obtaining self-aware capability parameters instantiated with respect to a current location of the autonomous driving vehicle, wherein the self-aware capability parameters are to be used to estimate the operational capability of the autonomous driving vehicle with respect to the current location;
estimating a preference of a passenger present in the autonomous driving vehicle with respect to vehicle motion; and
planning the motion of the autonomous driving vehicle based on the self-aware capability parameters and the preference of the passenger.
9 . The medium of claim 8 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying at least one intrinsic capability parameter that limits the operational ability of the autonomous driving vehicle due to conditions internal to the autonomous driving vehicle, the extrinsic capability parameters specifying at least one extrinsic capability parameter that limits the operational ability of the autonomous driving vehicle due to conditions external to the autonomous driving vehicle.
10 . The medium of claim 8 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous driving vehicle is currently associated with.
11 . The medium of claim 8 , wherein the preference of the passenger with respect to the vehicle motion is estimated based on at least one of:
an explicit indication of the preference;
an reaction of the passenger to the vehicle motion; and
a scenario relevant to the passenger.
12 . The medium of claim 11 , wherein the reaction of the passenger is estimated by:
obtaining, via one or more in-situ sensors, sensor data in one or more media types;
obtaining at least one feature associated with the passenger based on the sensor data;
identifying a reaction cue of the passenger based on at least one of
a visual based reaction cue based on some visual feature of the at least one feature, and
an acoustic based reaction cue based on some acoustic feature of the at least one feature; and
obtaining the reaction of the passenger to the vehicle motion based on the reaction cue of the passenger.
13 . The medium of claim 12 , wherein the reaction of the passenger to the vehicle motion is further evaluated based on at least one of an express statement, emotional state of the passenger inferred based on the visual and acoustic features of the at least one feature, and a combination thereof.
14 . The medium of claim 12 , wherein the scenario relevant to the passenger for inferring the preference of the passenger include at least one of:
a known event scheduled;
an event with an indicated urgency; and
certain information about the passenger.
15 . A system for motion planning for an autonomous driving vehicle, comprising:
a self-aware capability analyzer configured for obtaining self-aware capability parameters instantiated with respect to a current location of the autonomous driving vehicle, wherein the self-aware capability parameters are to be used to estimate the operational capability of the autonomous driving vehicle with respect to the current location;
a passenger observation analyzer configured for estimating a preference of a passenger present in the autonomous driving vehicle with respect to vehicle motion; and
a passenger motion adapter configured for planning motion of the autonomous driving vehicle based on the self-aware capability parameters and the preference of the passenger.
16 . The system of claim 15 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying at least one intrinsic capability parameter that limits the operational ability of the autonomous driving vehicle due to conditions internal to the autonomous driving vehicle, the extrinsic capability parameters specifying at least one extrinsic capability parameter that limits the operational ability of the autonomous driving vehicle due to conditions external to the autonomous driving vehicle.
17 . The system of claim 15 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous driving vehicle is currently associated with.
18 . The system of claim 15 , wherein the preference of the passenger with respect to the vehicle motion is estimated based on at least one of:
an explicit indication of the preference;
an reaction of the passenger to the vehicle motion; and
a scenario relevant to the passenger.
19 . The system of claim 18 , wherein the passenger observation analyzer comprises:
a sensor activator configured for activating one or more in-situ sensors to collect sensor data in one or more media types;
a passenger feature extractor configured for obtaining at least one feature associated with the passenger based on the sensor data;
at least one reaction cue estimator configured for obtaining at least one of
a visual based reaction cue based on some visual feature of the at least one feature, and
an acoustic based reaction cue based on some acoustic feature of the at least one feature; and
a user reaction generator configured for obtaining the reaction of the passenger to the vehicle motion based on the reaction cue of the passenger.
20 . The system of claim 19 , wherein the reaction of the passenger to the vehicle motion is further evaluated based on at least one of an express statement, emotional state inferred based on the visual and acoustic features of the at least one feature, and a combination thereof.
21 . The system of claim 19 , wherein the scenario relevant to the passenger for inferring the preference of the passenger include at least one of:
a known event scheduled;
an event with an indicated urgency; and
certain information about the passenger.